S2.Ep3 - LLM, pensare o prevedere? episode artwork

EPISODE · May 30, 2025 · 13 MIN

S2.Ep3 - LLM, pensare o prevedere?

from INNOVATIABLE · host Reti S.p.A.

Scopriamo come i Large Language Model (LLM) prevedono le parole successive in una frase basandosi su vasti dataset, utilizzando "embeddings" per mappare le relazioni tra le parole in uno spazio multidimensionale. Parliamo poi dell'architettura Retrieval-Augmented Generation (RAG) e altre tecniche per aggiornare i LLM con informazioni recenti. Ma anche GPT-4, Claude 3 e Gemini 1.5... Ascolta ora la puntata con Lorenzo Beliusse, Stefano Zaffaroni e Marco Acchini. 

Episode metadata supplied by the publisher feed · Published May 30, 2025

Embed this episode

Ready to play

S2.Ep3 - LLM, pensare o prevedere?

0:00 13:53

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of INNOVATIABLE?

This episode is 13 minutes long.

When was this INNOVATIABLE episode published?

This episode was published on May 30, 2025.

Can I download this INNOVATIABLE episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!